m-nzr commited on
Commit
75c44e3
·
verified ·
1 Parent(s): 60dba2c

Training in progress, epoch 1

Browse files
adapter_config.json CHANGED
@@ -3,6 +3,7 @@
3
  "auto_mapping": null,
4
  "base_model_name_or_path": "google/gemma-3-1b-pt",
5
  "bias": "none",
 
6
  "eva_config": null,
7
  "exclude_modules": null,
8
  "fan_in_fan_out": false,
@@ -17,21 +18,25 @@
17
  "lora_dropout": 0.05,
18
  "megatron_config": null,
19
  "megatron_core": "megatron.core",
20
- "modules_to_save": null,
 
 
 
21
  "peft_type": "LORA",
22
  "r": 16,
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
- "down_proj",
27
- "k_proj",
28
- "up_proj",
29
  "q_proj",
 
30
  "v_proj",
 
31
  "gate_proj",
32
- "o_proj"
 
33
  ],
34
  "task_type": "CAUSAL_LM",
 
35
  "use_dora": false,
36
  "use_rslora": false
37
  }
 
3
  "auto_mapping": null,
4
  "base_model_name_or_path": "google/gemma-3-1b-pt",
5
  "bias": "none",
6
+ "corda_config": null,
7
  "eva_config": null,
8
  "exclude_modules": null,
9
  "fan_in_fan_out": false,
 
18
  "lora_dropout": 0.05,
19
  "megatron_config": null,
20
  "megatron_core": "megatron.core",
21
+ "modules_to_save": [
22
+ "lm_head",
23
+ "embed_tokens"
24
+ ],
25
  "peft_type": "LORA",
26
  "r": 16,
27
  "rank_pattern": {},
28
  "revision": null,
29
  "target_modules": [
 
 
 
30
  "q_proj",
31
+ "up_proj",
32
  "v_proj",
33
+ "k_proj",
34
  "gate_proj",
35
+ "o_proj",
36
+ "down_proj"
37
  ],
38
  "task_type": "CAUSAL_LM",
39
+ "trainable_token_indices": null,
40
  "use_dora": false,
41
  "use_rslora": false
42
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44d6ffdd46293df1ea5a86f3b9fe99f58681c4f1e2748a1576fba3422c2a0b38
3
- size 52231312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8e32921bb7b9f5f3ff03489d2e08a6f988c9d94061910100d195497bfcb0abe
3
+ size 2468152240
chat_template.jinja ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{ bos_token }}
2
+ {%- if messages[0]['role'] == 'system' -%}
3
+ {%- if messages[0]['content'] is string -%}
4
+ {%- set first_user_prefix = messages[0]['content'] + '
5
+
6
+ ' -%}
7
+ {%- else -%}
8
+ {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
9
+
10
+ ' -%}
11
+ {%- endif -%}
12
+ {%- set loop_messages = messages[1:] -%}
13
+ {%- else -%}
14
+ {%- set first_user_prefix = "" -%}
15
+ {%- set loop_messages = messages -%}
16
+ {%- endif -%}
17
+ {%- for message in loop_messages -%}
18
+ {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
19
+ {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
20
+ {%- endif -%}
21
+ {%- if (message['role'] == 'assistant') -%}
22
+ {%- set role = "model" -%}
23
+ {%- else -%}
24
+ {%- set role = message['role'] -%}
25
+ {%- endif -%}
26
+ {{ '<start_of_turn>' + role + '
27
+ ' + (first_user_prefix if loop.first else "") }}
28
+ {%- if message['content'] is string -%}
29
+ {{ message['content'] | trim }}
30
+ {%- elif message['content'] is iterable -%}
31
+ {%- for item in message['content'] -%}
32
+ {%- if item['type'] == 'image' -%}
33
+ {{ '<start_of_image>' }}
34
+ {%- elif item['type'] == 'text' -%}
35
+ {{ item['text'] | trim }}
36
+ {%- endif -%}
37
+ {%- endfor -%}
38
+ {%- else -%}
39
+ {{ raise_exception("Invalid content type") }}
40
+ {%- endif -%}
41
+ {{ '<end_of_turn>
42
+ ' }}
43
+ {%- endfor -%}
44
+ {%- if add_generation_prompt -%}
45
+ {{'<start_of_turn>model
46
+ '}}
47
+ {%- endif -%}
runs/Jun07_13-25-30_19f1e0facf7a/events.out.tfevents.1749302746.19f1e0facf7a.549.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1df23b06247992957c6109b874ff7729e46800d268ca19786983f5389576267c
3
+ size 12619
tokenizer_config.json CHANGED
@@ -51325,7 +51325,6 @@
51325
  },
51326
  "boi_token": "<start_of_image>",
51327
  "bos_token": "<bos>",
51328
- "chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n {%- if messages[0]['content'] is string -%}\n {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n {%- else -%}\n {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n {%- set first_user_prefix = \"\" -%}\n {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif -%}\n {%- if (message['role'] == 'assistant') -%}\n {%- set role = \"model\" -%}\n {%- else -%}\n {%- set role = message['role'] -%}\n {%- endif -%}\n {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n {%- if message['content'] is string -%}\n {{ message['content'] | trim }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'image' -%}\n {{ '<start_of_image>' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{'<start_of_turn>model\n'}}\n{%- endif -%}\n",
51329
  "clean_up_tokenization_spaces": false,
51330
  "eoi_token": "<end_of_image>",
51331
  "eos_token": "<eos>",
 
51325
  },
51326
  "boi_token": "<start_of_image>",
51327
  "bos_token": "<bos>",
 
51328
  "clean_up_tokenization_spaces": false,
51329
  "eoi_token": "<end_of_image>",
51330
  "eos_token": "<eos>",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29d2866752cd438000e23cc6d9ba585925707bac0a25adf170ca2e729e88941e
3
  size 5688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a47e9d5bd2abe9a32d84fc3312911c3a1cec4ee5ebc1eedeb1eb106af5ae9570
3
  size 5688